Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    URL, I'm, if, listen, dest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    自己
    0.37
     கதாபா
    0.37
    自分
    0.36
     সম্পন্ন
    0.36
     selfishness
    0.36
     selfish
    0.35
    ]";
    0.35
     unpacked
    0.35
     sentença
    0.34
     ολο
    0.34
    POSITIVE LOGITS
     nedir
    0.39
    ason
    0.37
     nào
    0.37
     কিভাবে
    0.37
    gles
    0.36
    Why
    0.36
     ಎಂದ
    0.36
    harth
    0.36
    왤
    0.35
    testid
    0.35
    Act Density 0.000%

    No Known Activations